Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 273
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-273.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.766.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
1198 3237 5525 4593 4643 5697 2474 4072 4881 3337 4239 5127 3658 1825  996 4992 
  17   18   19   20   21   22   23   24   25 
3690 5179 3347 5121 4542 3323 2934 3512 2739 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt       tmax       tmin  longitud   latitud     altitud
[1,] -0.1040795 -0.8454533 -0.9058925 0.5746571 0.2885151  0.33451253
[2,]  0.8750336  0.3775844  0.3295735 0.2074481 0.2792705 -0.03224658

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud      tmax fecha_cnt   latitud      tmin 
0.9603377 0.9396375 0.9329319 0.9291338 0.9262232 0.9260460 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin             precip      
 Min.   : 1.000   Min.   :-53   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:123   1st Qu.:  26.00   1st Qu.:  6.00  
 Median : 3.000   Median :156   Median :  57.00   Median : 14.00  
 Mean   : 3.184   Mean   :153   Mean   :  54.15   Mean   : 19.43  
 3rd Qu.: 4.000   3rd Qu.:185   3rd Qu.:  83.00   3rd Qu.: 27.00  
 Max.   :12.000   Max.   :307   Max.   : 191.00   Max.   :371.00  
     nevada          prof_nieve          longitud        latitud       
 Min.   :0.00000   Min.   :   0.000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.00000   1st Qu.:   0.000   1st Qu.:39.01   1st Qu.:-5.3456  
 Median :0.00000   Median :   0.000   Median :41.11   Median :-3.1742  
 Mean   :0.00054   Mean   :   1.221   Mean   :40.63   Mean   :-2.6674  
 3rd Qu.:0.00000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.: 0.4914  
 Max.   :6.00000   Max.   :1834.000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 412.0  
 Mean   : 529.8  
 3rd Qu.: 775.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip      
 Min.   : 1.000   Min.   :  8.0   Min.   :-110.0   Min.   :  0.00  
 1st Qu.: 7.000   1st Qu.:182.0   1st Qu.:  86.0   1st Qu.:  2.00  
 Median : 9.000   Median :236.0   Median : 128.0   Median :  9.00  
 Mean   : 8.701   Mean   :229.4   Mean   : 121.9   Mean   : 15.28  
 3rd Qu.:11.000   3rd Qu.:283.0   3rd Qu.: 163.0   3rd Qu.: 21.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.0   Max.   :422.00  
     nevada            prof_nieve         longitud        latitud       
 Min.   :0.0000000   Min.   : 0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.0000   1st Qu.:38.95   1st Qu.:-4.8458  
 Median :0.0000000   Median : 0.0000   Median :40.95   Median :-2.3308  
 Mean   :0.0001704   Mean   : 0.0217   Mean   :40.50   Mean   :-2.2992  
 3rd Qu.:0.0000000   3rd Qu.: 0.0000   3rd Qu.:42.08   3rd Qu.: 0.5706  
 Max.   :3.0000000   Max.   :59.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.0  
 Median : 185.0  
 Mean   : 331.1  
 3rd Qu.: 611.0  
 Max.   :1894.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.0  
 1st Qu.:2.000   1st Qu.:129.0   1st Qu.: 30.00   1st Qu.:  5.0  
 Median :3.000   Median :159.0   Median : 59.00   Median : 13.0  
 Mean   :2.891   Mean   :159.2   Mean   : 57.76   Mean   : 18.1  
 3rd Qu.:4.000   3rd Qu.:187.0   3rd Qu.: 84.00   3rd Qu.: 24.0  
 Max.   :7.000   Max.   :307.0   Max.   :191.00   Max.   :371.0  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.5975  
 Median :0.000000   Median : 0.00000   Median :40.96   Median :-3.5556  
 Mean   :0.000587   Mean   : 0.09429   Mean   :40.51   Mean   :-2.8809  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.: 0.0406  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  52.0  
 Median : 336.0  
 Mean   : 391.9  
 3rd Qu.: 667.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip      
 Min.   : 1.000   Min.   :  8.0   Min.   :-110.0   Min.   :  0.00  
 1st Qu.: 7.000   1st Qu.:182.0   1st Qu.:  86.0   1st Qu.:  2.00  
 Median : 9.000   Median :236.0   Median : 128.0   Median :  9.00  
 Mean   : 8.701   Mean   :229.4   Mean   : 121.9   Mean   : 15.28  
 3rd Qu.:11.000   3rd Qu.:283.0   3rd Qu.: 163.0   3rd Qu.: 21.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.0   Max.   :422.00  
     nevada            prof_nieve         longitud        latitud       
 Min.   :0.0000000   Min.   : 0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.0000   1st Qu.:38.95   1st Qu.:-4.8458  
 Median :0.0000000   Median : 0.0000   Median :40.95   Median :-2.3308  
 Mean   :0.0001704   Mean   : 0.0217   Mean   :40.50   Mean   :-2.2992  
 3rd Qu.:0.0000000   3rd Qu.: 0.0000   3rd Qu.:42.08   3rd Qu.: 0.5706  
 Max.   :3.0000000   Max.   :59.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.0  
 Median : 185.0  
 Mean   : 331.1  
 3rd Qu.: 611.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.0   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 30.00   1st Qu.: -31.0   1st Qu.: 17.00  
 Median : 6.000   Median : 74.00   Median :   8.0   Median : 30.00  
 Mean   : 6.541   Mean   : 82.34   Mean   :  12.7   Mean   : 34.69  
 3rd Qu.:10.000   3rd Qu.:133.00   3rd Qu.:  58.0   3rd Qu.: 47.00  
 Max.   :12.000   Max.   :229.00   Max.   : 134.0   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  14.14   Mean   :41.95   Mean   :-0.2193   Mean   :2110  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.00   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.00   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.51   Mean   :217.2   Mean   :150.4   Mean   :  7.421   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:253.0   3rd Qu.:189.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :309.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03075   Mean   :28.37   Mean   :-16.05   Mean   : 520.9  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.0  
 1st Qu.:2.000   1st Qu.:129.0   1st Qu.: 30.00   1st Qu.:  5.0  
 Median :3.000   Median :159.0   Median : 59.00   Median : 13.0  
 Mean   :2.891   Mean   :159.2   Mean   : 57.76   Mean   : 18.1  
 3rd Qu.:4.000   3rd Qu.:187.0   3rd Qu.: 84.00   3rd Qu.: 24.0  
 Max.   :7.000   Max.   :307.0   Max.   :191.00   Max.   :371.0  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.5975  
 Median :0.000000   Median : 0.00000   Median :40.96   Median :-3.5556  
 Mean   :0.000587   Mean   : 0.09429   Mean   :40.51   Mean   :-2.8809  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.: 0.0406  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  52.0  
 Median : 336.0  
 Mean   : 391.9  
 3rd Qu.: 667.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax          tmin         precip           nevada 
 Min.   : 1.000   Min.   :164   Min.   : 65   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:242   1st Qu.:129   1st Qu.:  1.00   1st Qu.:0  
 Median : 7.000   Median :274   Median :154   Median :  6.00   Median :0  
 Mean   : 7.206   Mean   :272   Mean   :155   Mean   : 10.92   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:302   3rd Qu.:181   3rd Qu.: 15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.:-4.8458   1st Qu.:  35.0  
 Median : 0.00000   Median :40.93   Median :-2.0392   Median : 127.0  
 Mean   : 0.00361   Mean   :40.46   Mean   :-2.2614   Mean   : 300.7  
 3rd Qu.: 0.00000   3rd Qu.:42.07   3rd Qu.: 0.5706   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.0   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 30.00   1st Qu.: -31.0   1st Qu.: 17.00  
 Median : 6.000   Median : 74.00   Median :   8.0   Median : 30.00  
 Mean   : 6.541   Mean   : 82.34   Mean   :  12.7   Mean   : 34.69  
 3rd Qu.:10.000   3rd Qu.:133.00   3rd Qu.:  58.0   3rd Qu.: 47.00  
 Max.   :12.000   Max.   :229.00   Max.   : 134.0   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  14.14   Mean   :41.95   Mean   :-0.2193   Mean   :2110  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:129.0   1st Qu.:  41.00   1st Qu.:  6.00  
 Median :11.00   Median :166.0   Median :  73.00   Median : 15.00  
 Mean   :10.97   Mean   :164.8   Mean   :  71.61   Mean   : 21.91  
 3rd Qu.:12.00   3rd Qu.:200.0   3rd Qu.: 102.00   3rd Qu.: 30.00  
 Max.   :12.00   Max.   :284.0   Max.   : 187.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.96   Median :-2.4544  
 Mean   :0.0004291   Mean   : 0.04915   Mean   :40.55   Mean   :-2.3567  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 261.0  
 Mean   : 377.3  
 3rd Qu.: 667.0  
 Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.0  
 1st Qu.:2.000   1st Qu.:129.0   1st Qu.: 30.00   1st Qu.:  5.0  
 Median :3.000   Median :159.0   Median : 59.00   Median : 13.0  
 Mean   :2.891   Mean   :159.2   Mean   : 57.76   Mean   : 18.1  
 3rd Qu.:4.000   3rd Qu.:187.0   3rd Qu.: 84.00   3rd Qu.: 24.0  
 Max.   :7.000   Max.   :307.0   Max.   :191.00   Max.   :371.0  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-5.5975  
 Median :0.000000   Median : 0.00000   Median :40.96   Median :-3.5556  
 Mean   :0.000587   Mean   : 0.09429   Mean   :40.51   Mean   :-2.8809  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.: 0.0406  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  52.0  
 Median : 336.0  
 Mean   : 391.9  
 3rd Qu.: 667.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax          tmin         precip           nevada 
 Min.   : 1.000   Min.   :164   Min.   : 65   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:242   1st Qu.:129   1st Qu.:  1.00   1st Qu.:0  
 Median : 7.000   Median :274   Median :154   Median :  6.00   Median :0  
 Mean   : 7.206   Mean   :272   Mean   :155   Mean   : 10.92   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:302   3rd Qu.:181   3rd Qu.: 15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.:-4.8458   1st Qu.:  35.0  
 Median : 0.00000   Median :40.93   Median :-2.0392   Median : 127.0  
 Mean   : 0.00361   Mean   :40.46   Mean   :-2.2614   Mean   : 300.7  
 3rd Qu.: 0.00000   3rd Qu.:42.07   3rd Qu.: 0.5706   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.0   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 30.00   1st Qu.: -31.0   1st Qu.: 17.00  
 Median : 6.000   Median : 74.00   Median :   8.0   Median : 30.00  
 Mean   : 6.541   Mean   : 82.34   Mean   :  12.7   Mean   : 34.69  
 3rd Qu.:10.000   3rd Qu.:133.00   3rd Qu.:  58.0   3rd Qu.: 47.00  
 Max.   :12.000   Max.   :229.00   Max.   : 134.0   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  14.14   Mean   :41.95   Mean   :-0.2193   Mean   :2110  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:129.0   1st Qu.:  41.00   1st Qu.:  6.00  
 Median :11.00   Median :166.0   Median :  73.00   Median : 15.00  
 Mean   :10.97   Mean   :164.8   Mean   :  71.61   Mean   : 21.91  
 3rd Qu.:12.00   3rd Qu.:200.0   3rd Qu.: 102.00   3rd Qu.: 30.00  
 Max.   :12.00   Max.   :284.0   Max.   : 187.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.0000000   Median : 0.00000   Median :40.96   Median :-2.4544  
 Mean   :0.0004291   Mean   : 0.04915   Mean   :40.55   Mean   :-2.3567  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 261.0  
 Mean   : 377.3  
 3rd Qu.: 667.0  
 Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :1.000   Min.   :100.0   Min.   :-17.0   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:167.0   1st Qu.: 76.0   1st Qu.:  3.00   1st Qu.:0  
 Median :3.000   Median :191.0   Median :101.0   Median : 11.00   Median :0  
 Mean   :3.174   Mean   :196.7   Mean   :100.7   Mean   : 15.73   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:224.0   3rd Qu.:125.0   3rd Qu.: 22.00   3rd Qu.:0  
 Max.   :7.000   Max.   :307.0   Max.   :191.0   Max.   :259.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.00  
 1st Qu.: 0.00000   1st Qu.:36.50   1st Qu.:-6.332   1st Qu.: 19.00  
 Median : 0.00000   Median :36.83   Median :-5.616   Median : 32.00  
 Mean   : 0.01769   Mean   :36.92   Mean   :-5.389   Mean   : 75.78  
 3rd Qu.: 0.00000   3rd Qu.:37.26   3rd Qu.:-4.846   3rd Qu.: 90.00  
 Max.   :34.00000   Max.   :39.47   Max.   :-1.169   Max.   :582.00  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:122.0   1st Qu.: 24.00   1st Qu.:  6.00  
 Median :3.000   Median :152.0   Median : 52.00   Median : 13.00  
 Mean   :2.831   Mean   :151.2   Mean   : 48.54   Mean   : 18.61  
 3rd Qu.:4.000   3rd Qu.:179.0   3rd Qu.: 75.00   3rd Qu.: 25.00  
 Max.   :7.000   Max.   :282.0   Max.   :143.00   Max.   :371.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.41   1st Qu.:-4.1153  
 Median :0.000000   Median : 0.0000   Median :41.52   Median :-2.4831  
 Mean   :0.000713   Mean   : 0.1107   Mean   :41.28   Mean   :-2.3430  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:42.44   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 508.0  
 Mean   : 459.7  
 3rd Qu.: 704.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax          tmin         precip           nevada 
 Min.   : 1.000   Min.   :164   Min.   : 65   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:242   1st Qu.:129   1st Qu.:  1.00   1st Qu.:0  
 Median : 7.000   Median :274   Median :154   Median :  6.00   Median :0  
 Mean   : 7.206   Mean   :272   Mean   :155   Mean   : 10.92   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:302   3rd Qu.:181   3rd Qu.: 15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.:-4.8458   1st Qu.:  35.0  
 Median : 0.00000   Median :40.93   Median :-2.0392   Median : 127.0  
 Mean   : 0.00361   Mean   :40.46   Mean   :-2.2614   Mean   : 300.7  
 3rd Qu.: 0.00000   3rd Qu.:42.07   3rd Qu.: 0.5706   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax             tmin            precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.0   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 30.00   1st Qu.: -31.0   1st Qu.: 17.00  
 Median : 6.000   Median : 74.00   Median :   8.0   Median : 30.00  
 Mean   : 6.541   Mean   : 82.34   Mean   :  12.7   Mean   : 34.69  
 3rd Qu.:10.000   3rd Qu.:133.00   3rd Qu.:  58.0   3rd Qu.: 47.00  
 Max.   :12.000   Max.   :229.00   Max.   : 134.0   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  14.14   Mean   :41.95   Mean   :-0.2193   Mean   :2110  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:110.0   1st Qu.:  23.00   1st Qu.:  7.00  
 Median :11.00   Median :140.0   Median :  54.00   Median : 16.00  
 Mean   :10.96   Mean   :144.7   Mean   :  51.45   Mean   : 23.64  
 3rd Qu.:12.00   3rd Qu.:179.0   3rd Qu.:  82.00   3rd Qu.: 31.00  
 Max.   :12.00   Max.   :265.0   Max.   : 140.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud      
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.18   Min.   :-8.649  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:40.48   1st Qu.:-5.498  
 Median :0.0000000   Median : 0.00000   Median :41.70   Median :-3.764  
 Mean   :0.0008031   Mean   : 0.06487   Mean   :41.53   Mean   :-3.621  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.59   3rd Qu.:-1.885  
 Max.   :3.0000000   Max.   :40.00000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 442.0  
 Median : 639.0  
 Mean   : 607.5  
 3rd Qu.: 846.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 8.00   Min.   : 68.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:161.0   1st Qu.: 66.00   1st Qu.:  4.00   1st Qu.:0  
 Median :11.00   Median :185.0   Median : 96.00   Median : 13.00   Median :0  
 Mean   :10.97   Mean   :187.7   Mean   : 94.73   Mean   : 19.92   Mean   :0  
 3rd Qu.:12.00   3rd Qu.:218.0   3rd Qu.:124.00   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :12.00   Max.   :284.0   Max.   :187.00   Max.   :206.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.:-3.7892   1st Qu.: 17.0  
 Median : 0.00000   Median :39.49   Median : 0.4731   Median : 68.6  
 Mean   : 0.03112   Mean   :39.44   Mean   :-0.9058   Mean   :113.2  
 3rd Qu.: 0.00000   3rd Qu.:41.42   3rd Qu.: 1.3842   3rd Qu.:158.0  
 Max.   :59.00000   Max.   :43.36   Max.   : 4.2156   Max.   :691.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :128   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.603   Mean   :138   Mean   : 60.53   Mean   : 11.63   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183   3rd Qu.: 98.00   3rd Qu.: 14.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253   Max.   :159.00   Max.   :309.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1753   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :1.000   Min.   :100.0   Min.   :-17.0   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:167.0   1st Qu.: 76.0   1st Qu.:  3.00   1st Qu.:0  
 Median :3.000   Median :191.0   Median :101.0   Median : 11.00   Median :0  
 Mean   :3.174   Mean   :196.7   Mean   :100.7   Mean   : 15.73   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:224.0   3rd Qu.:125.0   3rd Qu.: 22.00   3rd Qu.:0  
 Max.   :7.000   Max.   :307.0   Max.   :191.0   Max.   :259.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.00  
 1st Qu.: 0.00000   1st Qu.:36.50   1st Qu.:-6.332   1st Qu.: 19.00  
 Median : 0.00000   Median :36.83   Median :-5.616   Median : 32.00  
 Mean   : 0.01769   Mean   :36.92   Mean   :-5.389   Mean   : 75.78  
 3rd Qu.: 0.00000   3rd Qu.:37.26   3rd Qu.:-4.846   3rd Qu.: 90.00  
 Max.   :34.00000   Max.   :39.47   Max.   :-1.169   Max.   :582.00  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip      
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:122.0   1st Qu.: 24.00   1st Qu.:  6.00  
 Median :3.000   Median :152.0   Median : 52.00   Median : 13.00  
 Mean   :2.831   Mean   :151.2   Mean   : 48.54   Mean   : 18.61  
 3rd Qu.:4.000   3rd Qu.:179.0   3rd Qu.: 75.00   3rd Qu.: 25.00  
 Max.   :7.000   Max.   :282.0   Max.   :143.00   Max.   :371.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.41   1st Qu.:-4.1153  
 Median :0.000000   Median : 0.0000   Median :41.52   Median :-2.4831  
 Mean   :0.000713   Mean   : 0.1107   Mean   :41.28   Mean   :-2.3430  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:42.44   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 508.0  
 Mean   : 459.7  
 3rd Qu.: 704.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.00   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.00   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.49   Mean   :233.8   Mean   :169.3   Mean   :  6.536   Mean   :0  
 3rd Qu.: 9.00   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.00   Max.   :356.0   Max.   :244.0   Max.   :145.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003511   Mean   :28.38   Mean   :-15.96   Mean   :131.9  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   :171.0   Min.   : 65.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 5.000   1st Qu.:246.0   1st Qu.:134.0   1st Qu.:  2.00   1st Qu.:0  
 Median : 7.000   Median :276.0   Median :165.0   Median :  7.00   Median :0  
 Mean   : 6.695   Mean   :270.7   Mean   :161.2   Mean   : 11.26   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:298.0   3rd Qu.:189.0   3rd Qu.: 16.00   3rd Qu.:0  
 Max.   :12.000   Max.   :386.0   Max.   :254.0   Max.   :320.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   : 0.00000   Min.   :37.79   Min.   :-2.9056   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.: 0.3264   1st Qu.: 25.0  
 Median : 0.00000   Median :41.15   Median : 0.6350   Median : 71.0  
 Mean   : 0.00338   Mean   :40.46   Mean   : 0.8364   Mean   :148.7  
 3rd Qu.: 0.00000   3rd Qu.:41.66   3rd Qu.: 1.9625   3rd Qu.:247.0  
 Max.   :38.00000   Max.   :43.36   Max.   : 4.2156   Max.   :953.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :164.0   Min.   : 67.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:240.0   1st Qu.:127.0   1st Qu.:  1.00   1st Qu.:0  
 Median : 8.000   Median :272.0   Median :148.0   Median :  6.00   Median :0  
 Mean   : 7.588   Mean   :272.9   Mean   :150.4   Mean   : 10.67   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:305.0   3rd Qu.:172.0   3rd Qu.: 15.00   3rd Qu.:0  
 Max.   :11.000   Max.   :403.0   Max.   :250.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.649   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.84   1st Qu.:-5.879   1st Qu.:  52.0  
 Median : 0.00000   Median :40.84   Median :-4.127   Median : 370.0  
 Mean   : 0.00378   Mean   :40.46   Mean   :-4.573   Mean   : 414.1  
 3rd Qu.: 0.00000   3rd Qu.:42.59   3rd Qu.:-3.450   3rd Qu.: 687.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 2.438   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 2.000   Min.   :-20.0   Min.   :-80.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.: 68.0   1st Qu.:  8.00   1st Qu.: 16.00   1st Qu.:0  
 Median : 9.000   Median :113.0   Median : 42.00   Median : 28.00   Median :0  
 Mean   : 8.622   Mean   :110.6   Mean   : 38.76   Mean   : 32.82   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:155.0   3rd Qu.: 77.00   3rd Qu.: 43.00   3rd Qu.:0  
 Max.   :12.000   Max.   :229.0   Max.   :134.00   Max.   :171.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud    
 Min.   :  0.000   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :  0.000   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :  3.166   Mean   :41.92   Mean   :-0.2785   Mean   :2093  
 3rd Qu.:  0.000   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :382.000   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:  9.0   1st Qu.: -52.00   1st Qu.: 19.00  
 Median : 3.000   Median : 31.0   Median : -34.00   Median : 34.00  
 Mean   : 2.727   Mean   : 30.6   Mean   : -35.04   Mean   : 38.13  
 3rd Qu.: 4.000   3rd Qu.: 54.0   3rd Qu.: -13.00   3rd Qu.: 52.00  
 Max.   :12.000   Max.   :120.0   Max.   :  56.00   Max.   :180.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1405  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.38   Median : 0.9844   Median :2228  
 Mean   :0   Mean   :  34.26   Mean   :42.00   Mean   :-0.1108   Mean   :2141  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 7.00   Min.   :  8.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:110.0   1st Qu.:  23.00   1st Qu.:  7.00  
 Median :11.00   Median :140.0   Median :  54.00   Median : 16.00  
 Mean   :10.96   Mean   :144.7   Mean   :  51.45   Mean   : 23.64  
 3rd Qu.:12.00   3rd Qu.:179.0   3rd Qu.:  82.00   3rd Qu.: 31.00  
 Max.   :12.00   Max.   :265.0   Max.   : 140.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud      
 Min.   :0.0000000   Min.   : 0.00000   Min.   :37.18   Min.   :-8.649  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:40.48   1st Qu.:-5.498  
 Median :0.0000000   Median : 0.00000   Median :41.70   Median :-3.764  
 Mean   :0.0008031   Mean   : 0.06487   Mean   :41.53   Mean   :-3.621  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.59   3rd Qu.:-1.885  
 Max.   :3.0000000   Max.   :40.00000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 442.0  
 Median : 639.0  
 Mean   : 607.5  
 3rd Qu.: 846.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 8.00   Min.   : 68.0   Min.   :-29.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:161.0   1st Qu.: 66.00   1st Qu.:  4.00   1st Qu.:0  
 Median :11.00   Median :185.0   Median : 96.00   Median : 13.00   Median :0  
 Mean   :10.97   Mean   :187.7   Mean   : 94.73   Mean   : 19.92   Mean   :0  
 3rd Qu.:12.00   3rd Qu.:218.0   3rd Qu.:124.00   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :12.00   Max.   :284.0   Max.   :187.00   Max.   :206.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492   Min.   :  1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.:-3.7892   1st Qu.: 17.0  
 Median : 0.00000   Median :39.49   Median : 0.4731   Median : 68.6  
 Mean   : 0.03112   Mean   :39.44   Mean   :-0.9058   Mean   :113.2  
 3rd Qu.: 0.00000   3rd Qu.:41.42   3rd Qu.: 1.3842   3rd Qu.:158.0  
 Max.   :59.00000   Max.   :43.36   Max.   : 4.2156   Max.   :691.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)